CXL Consortium releases Compute Express Link 4.0 specification

The CXL Consortium has published the Compute Express Link 4.0 specification to address growing data center workload demands. The release promises doubled bandwidth versus the prior generation and adds new capabilities for coherent memory connectivity.

The CXL Consortium, an industry standard organization that develops and promotes an open coherent interconnection for heterogeneous memory and computing solutions, announced the release of the Compute Express Link 4.0 specification. The specification is presented as a response to increasing demands from emerging workloads placed on todayu2019s data centers, positioning the standard as a foundation for improved memory and device connectivity in heterogeneous architectures.

Derek Rohde, CXL Consortium president and treasurer and principal engineer at NVIDIA, characterized the release as a milestone for advancing coherent memory connectivity. According to the announcement, the CXL 4.0 specification doubles the bandwidth over the previous generation and introduces powerful new features. The consortium framed the update as the result of member companiesu2019 collaboration to produce open standards that enable broader compliance and interoperability across implementations.

The consortium emphasized that the specification is intended to empower data center innovation and help the industry scale for future usage models. By promoting an open, coherent interconnect, the CXL 4.0 release aims to support heterogeneous memory and computing solutions while providing a common framework for compliance and interoperability. The announcement highlights the consortiumu2019s role in coordinating industry efforts to meet evolving workload requirements without detailing specific technical changes beyond the reported bandwidth increase and new feature set.

68

Impact Score

The new dictionary of Artificial Intelligence reliability

As organizations move models from experimentation to production, the question shifts from “can we build it?” to “can we trust it?” This field guide defines the terms that shape Artificial Intelligence reliability across performance, data quality, system reliability, explainability, operations, and governance.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.